Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    geometrical shapes and points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ion
    -0.08
    -compose
    -0.08
     reasonable
    -0.08
    -client
    -0.07
    reasonable
    -0.07
     respectful
    -0.07
    categor
    -0.07
    -achọ
    -0.07
     sprint
    -0.07
    	NULL
    -0.07
    POSITIVE LOGITS
    ictured
    0.11
     pictured
    0.10
     representing
    0.09
     predstavlj
    0.09
    工作人员
    0.09
     tort
    0.09
     Öff
    0.09
    िनिध
    0.08
     представляет
    0.08
     टिप
    0.08
    Act Density 0.026%

    No Known Activations